SAL-CNN: Estimate the Remaining Useful Life of Bearings Using Time-frequency Information

TL;DR

This paper introduces SAL-CNN, an end-to-end deep learning approach utilizing time-frequency analysis and attention mechanisms to accurately predict the remaining useful life of bearings, improving reliability in industrial systems.

Contribution

The paper presents a novel SAL-CNN model combining STFT, LSTM, CNN, and attention modules for RUL prediction, with demonstrated effectiveness on real datasets.

Findings

Outperforms existing methods on the 2012PHM dataset

Effective integration of time-frequency analysis and attention mechanisms

Provides interpretability of the prediction process

Abstract

In modern industrial production, the prediction ability of the remaining useful life (RUL) of bearings directly affects the safety and stability of the system. Traditional methods require rigorous physical modeling and perform poorly for complex systems. In this paper, an end-to-end RUL prediction method is proposed, which uses short-time Fourier transform (STFT) as preprocessing. Considering the time correlation of signal sequences, a long and short-term memory network is designed in CNN, incorporating the convolutional block attention module, and understanding the decision-making process of the network from the interpretability level. Experiments were carried out on the 2012PHM dataset and compared with other methods, and the results proved the effectiveness of the method.